NVIDIA · 1-800-BAD-CODE · Nov 25, 2022 · Nov 25, 2022 · Nov 26, 2022 · Nov 19, 2022
diff --git a/.github/labeler.yml b/.github/labeler.yml
@@ -0,0 +1,5 @@
+ASR:
+- nemo/collections/asr/**/*
+
+NLP:
+- nemo/collections/nlp/**/*
diff --git a/.github/workflows/labeler.yml b/.github/workflows/labeler.yml
@@ -0,0 +1,14 @@
+name: "Pull Request Labeler"
+on:
+- pull_request_target
+
+jobs:
+  triage:
+    permissions:
+      contents: read
+      pull-requests: write
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/labeler@v4
+      with:
+        repo-token: "${{ secrets.GITHUB_TOKEN }}"
diff --git a/docs/source/asr/examples/kinyarwanda_asr.rst b/docs/source/asr/examples/kinyarwanda_asr.rst
@@ -483,7 +483,7 @@ The figure below shows the training dynamics when we train Kinyarwanda models **
     .. image:: ../images/kinyarwanda_from_scratch.png
         :align: center
         :alt: Training dynamics of Kinyarwanda models trained from scratch
-        :scale: 50%
+        :width: 800px
 
 Finetuning from another model
 #############################
@@ -530,7 +530,7 @@ The figure below compares the training dynamics for three Conformer-Transducer m
     .. image:: ../images/kinyarwanda_finetuning.png
         :align: center
         :alt: Training dynamics of Kinyarwanda models trained from scratch and finetuned from different pretrained checkpoints
-        :scale: 50%
+        :width: 800px
 
 ************************
 Inference and evaluation

diff --git a/docs/source/index.rst b/docs/source/index.rst
@@ -72,7 +72,7 @@ NVIDIA NeMo User Guide
 
 
 .. toctree::
-   :maxdepth: 2
+   :maxdepth: 3
    :caption: Tools
    :name: Tools
 

diff --git a/docs/source/nlp/dialogue.rst b/docs/source/nlp/dialogue.rst
@@ -13,6 +13,7 @@ In particular, we wanted to decouple the task-dependent, model-independent compo
 
 .. image:: dialogue_UML.png
   :alt: Dialogue-UML
+  :width: 800px
 
 **Supported Tasks** 
 

diff --git a/docs/source/nlp/entity_linking.rst b/docs/source/nlp/entity_linking.rst
@@ -15,6 +15,7 @@ be used to build a knowledge base embedding index.
 
 .. image:: https://github.com/NVIDIA/NeMo/blob/entity-linking-documentation/docs/source/nlp/entity_linking_overview.jpg
   :alt: Entity-Linking-Overview
+  :width: 800px
 
 Our BERT-base + Self Alignment Pretraining implementation allows you to train an entity linking encoder. We also provide example code
 on building an index with `Medical UMLS <https://www.nlm.nih.gov/research/umls/index.html>`_ concepts `NeMo/examples/nlp/entity_linking/build_index.py <https://github.com/NVIDIA/NeMo/tree/stable/examples/nlp/entity_linking/build_index.py>`__.

diff --git a/docs/source/nlp/nemo_megatron/parallelisms.rst b/docs/source/nlp/nemo_megatron/parallelisms.rst
@@ -10,6 +10,7 @@ Distributed Data parallelism
 
 .. image:: images/ddp.gif
     :align: center
+    :width: 800px
     :alt: Distributed Data Parallel
 
 
@@ -18,20 +19,23 @@ Tensor Parallelism
 
 .. image:: images/tp.gif
     :align: center
+    :width: 800px
     :alt: Tensor Parallel
 
 Pipeline Parallelism
 ^^^^^^^^^^^^^^^^^^^^
 
 .. image:: images/pp.gif
     :align: center
+    :width: 800px
     :alt: Pipeline Parallel
 
 Sequence Parallelism
 ^^^^^^^^^^^^^^^^^^^^
 
 .. image:: images/sp.gif
     :align: center
+    :width: 800px
     :alt: Sqeuence Parallel
 
 Parallelism nomenclature
@@ -41,4 +45,5 @@ When reading and modifying NeMo Megatron code you will encounter the following t
 
 .. image:: images/pnom.gif
     :align: center
+    :width: 800px
     :alt: Parallelism nomenclature
diff --git a/docs/source/nlp/question_answering.rst b/docs/source/nlp/question_answering.rst
@@ -72,6 +72,7 @@ Similarly, the BaseQAModel module handles common model tasks like creating datal
 
 .. image:: question_answering_arch.png
   :alt: Question-Answerin-Architecture
+  :width: 800px
 
 Configuration
 =============

diff --git a/docs/source/nlp/text_normalization/wfst/wfst_text_normalization.rst b/docs/source/nlp/text_normalization/wfst/wfst_text_normalization.rst
@@ -182,4 +182,4 @@ References
 .. bibliography:: ../tn_itn_all.bib
     :style: plain
     :labelprefix: TEXTPROCESSING-NORM
-    :keyprefix: textprocessing-norm-
+    :keyprefix: textprocessing-norm-
diff --git a/docs/source/nlp/text_normalization/wfst/wfst_text_processing_deployment.rst b/docs/source/nlp/text_normalization/wfst/wfst_text_processing_deployment.rst
@@ -96,4 +96,4 @@ References
 .. bibliography:: ../tn_itn_all.bib
     :style: plain
     :labelprefix: TEXTPROCESSING-DEPLOYMENT
-    :keyprefix: textprocessing-deployment-
+    :keyprefix: textprocessing-deployment-
diff --git a/docs/source/tools/comparison_tool.rst b/docs/source/tools/comparison_tool.rst
@@ -0,0 +1,153 @@
+Comparison tool for ASR Models
+==============================
+
+The Comparison Tool (CT) allows to compare predictions of different ASR models at word accuracy level. 
+
++--------------------------------------------------------------------------------------------------------------------------+
+| **Comparison tool features:**                                                                                            |
++--------------------------------------------------------------------------------------------------------------------------+
+| navigation across dataset's vocabulary using an interactive datatable that supports sorting and filtering                |
++--------------------------------------------------------------------------------------------------------------------------+
+| interactive visualization of model's accuracy                                                                            |
++--------------------------------------------------------------------------------------------------------------------------+
+| visual comparison of predictions of different models                                                                     |
++--------------------------------------------------------------------------------------------------------------------------+
+
+Getting Started
+---------------
+The Comparison Tool is integrated in NeMo Speech Data Explorer (SDE) that could be found at `NeMo/tools/speech_data_explorer <https://github.com/NVIDIA/NeMo/tree/main/tools/speech_data_explorer>`__.
+
+Please install the SDE requirements:
+
+.. code-block:: bash
+
+    pip install -r tools/speech_data_explorer/requirements.txt
+
+Then run:
+
+.. code-block:: bash
+
+    python tools/speech_data_explorer/data_explorer.py -h
+
+    usage: data_explorer.py [-h] [--vocab VOCAB] [--port PORT] [--disable-caching-metrics] [--estimate-audio-metrics] [--debug] manifest
+
+    Speech Data Explorer
+
+    positional arguments:
+    manifest              path to JSON manifest file
+
+    optional arguments:
+    -h, --help            show this help message and exit
+    --vocab VOCAB         optional vocabulary to highlight OOV words
+    --port PORT           serving port for establishing connection
+    --disable-caching-metrics
+                            disable caching metrics for errors analysis
+    --estimate-audio-metrics, -a
+                            estimate frequency bandwidth and signal level of audio recordings
+    --debug, -d           enable debug mode
+    --audio-base-path A base path for the relative paths in manifest. It defaults to manifest path.
+    --names_compared, -nc names of the two fields that will be compared, example: pred_text_contextnet pred_text_conformer.
+    --show_statistics, -shst field name for which you want to see statistics (optional). Example: pred_text_contextnet.
+
+CT takes a JSON manifest file (that describes speech datasets in NeMo) as an input. It should contain the following fields:
+
+* `audio_filepath` (path to audio file)
+* `duration` (duration of the audio file in seconds)
+* `text` (reference transcript)
+* `pred_text_<model_1_name>`
+* `pred_text_<model_2_name>`
+
+SDE supports any extra custom fields in the JSON manifest. If the field is numeric, then SDE can visualize its distribution across utterances.
+
+JSON manifest has attribute `pred_text`, SDE interprets it as a predicted ASR transcript and computes error analysis metrics.
+If you want SDE to analyse another prediction field, then please use `--show_statistics` argument.
+
+User Interface
+--------------
+
+SDE has three pages if `--names_compared` argument is not empty:
+
+* `Statistics` (to display global statistics and aggregated error metrics)
+
+    .. image:: images/sde_base_stats.png
+        :align: center
+        :width: 800px
+        :alt: SDE Statistics
+
+
+* `Samples` (to allow navigation across the entire dataset and exploration of individual utterances)
+
+    .. image:: images/sde_player.png
+        :align: center
+        :width: 800px
+        :alt: SDE Statistics
+
+* `Comparison tool` (to explore predictions at word level)
+
+    .. image:: images/scrsh_2.png
+        :align: center
+        :width: 800px
+        :alt: Comparison tool
+
+
+CT has an interactive datatable for dataset's vocabulary (that supports navigation, filtering, and sorting):
+
+
+* Data (that visualizes all dataset's words and adds each one's accuracy)
+
+    .. image:: images/scrsh_3.png
+        :align: center
+        :width: 800px
+        :alt: Data
+
+CT supports all operations, that present in SDE, and allows combination of filtering expressions with "or" and "and" operations
+
+* filtering (by entering a filtering expression in a cell below the header's cell)
+
+    .. image:: images/scrsh_4.png
+        :align: center
+        :width: 800px
+        :alt: Filtering
+
+
+Analysis of Speech Datasets
+---------------------------
+
+If there is a pre-trained ASR model, then the JSON manifest file can be extended with ASR predicted transcripts:
+
+.. code-block:: bash
+
+    python examples/asr/transcribe_speech.py pretrained_name=<ASR_MODEL_NAME> dataset_manifest=<JSON_FILENAME> append_pred=False pred_name_postfix=<model_name_1>
+
+
+More information about transcribe_speech parameters is available in the code: `NeMo/examples/asr/transcribe_speech.py <https://github.com/NVIDIA/NeMo/blob/main/examples/asr/transcribe_speech.py>`__.
+.
+
+    .. image:: images/scrsh_2.png
+        :align: center
+        :width: 800px
+        :alt: fields
+
+Fields 1 and 2 are responsible for what will be displayed on the horizontal and vertical axes.
+
+Fields 3 and 4 allow you to convert any available numeric parameter into color and size, respectively.
+
+Fields 5 and 6 are responsible for point spacing. Some data points might have the same coordinates on both axes, in which case there will be an overlap, and in order to be able to explore each point, the option for their spreading was added.
+
+    .. image:: images/scrsh_5.png
+        :align: center
+        :width: 800px
+        :alt: dot spacing
+
+Point spacing works as follows: a small random value is added to all point coordinates, the value of which is limited by the "radius" parameter, which can be set manually.
+
+    .. image:: images/scrsh_9.png
+        :align: center
+        :width: 800px
+        :alt: Example
+
+In this case, all points lying above the diagonal have higher accuracy with the model displayed on the vertical axis, and all points below the diagonal were recognized better with the model displayed on the horizontal axis.
+
+Points marked with circles should be explored first.
+
+Words in the first quarter were well recognized by both models, and conversely, words in the third quarter were poorly recognized by both models.
diff --git a/docs/source/tools/images/scrsh_2.png b/docs/source/tools/images/scrsh_2.png
diff --git a/docs/source/tools/images/scrsh_3.png b/docs/source/tools/images/scrsh_3.png
diff --git a/docs/source/tools/images/scrsh_4.png b/docs/source/tools/images/scrsh_4.png
diff --git a/docs/source/tools/images/scrsh_5.png b/docs/source/tools/images/scrsh_5.png
diff --git a/docs/source/tools/images/scrsh_9.png b/docs/source/tools/images/scrsh_9.png
diff --git a/docs/source/tools/intro.rst b/docs/source/tools/intro.rst
@@ -9,5 +9,6 @@ NeMo provides a set of tools useful for developing Automatic Speech Recognitions
 
    ctc_segmentation
    speech_data_explorer
+   comparison_tool
 
 
diff --git a/docs/source/tools/speech_data_explorer.rst b/docs/source/tools/speech_data_explorer.rst
@@ -83,15 +83,17 @@ SDE application has two pages:
 
     .. image:: images/sde_base_stats.png
         :align: center
+        :width: 800px
         :alt: SDE Statistics
-        :scale: 50%
+
 
 * `Samples` (to allow navigation across the entire dataset and exploration of individual utterances)
 
     .. image:: images/sde_player.png
         :align: center
+        :width: 800px
         :alt: SDE Statistics
-        :scale: 50%
+
 
 Plotly Dash Datatable provides core SDE's interactive features (navigation, filtering, and sorting).
 SDE has two datatables:
@@ -100,38 +102,43 @@ SDE has two datatables:
 
     .. image:: images/sde_words.png
         :align: center
+        :width: 800px
         :alt: Vocabulary
-        :scale: 50%
+
 
 * Data (that visualizes all dataset's utterances on `Samples` page)
 
     .. image:: images/sde_utterances.png
         :align: center
+        :width: 800px
         :alt: Data
-        :scale: 50%
+
 
 Every column of the DataTable has the following interactive features:
 
 * toggling off (by clicking on the `eye` icon in the column's header cell) or on (by clicking on the `Toggle Columns` button below the table)
 
     .. image:: images/datatable_toggle.png
         :align: center
+        :width: 800px
         :alt: Toggling
-        :scale: 80%
+
 
 * sorting (by clicking on small triangle icons in the column's header cell): unordered (two triangles point up and down), ascending (a triangle points up), descending (a triangle points down)
 
     .. image:: images/datatable_sort.png
         :align: center
+        :width: 800px
         :alt: Sorting
-        :scale: 80%
+
 
 * filtering (by entering a filtering expression in a cell below the header's cell): SDE supports ``<``, ``>``, ``<=``, ``>=``, ``=``, ``!=``, and ``contains`` operators; to match a specific substring, the quoted substring can be used as a filtering expression
 
     .. image:: images/datatable_filter.png
         :align: center
+        :width: 800px
         :alt: Filtering
-        :scale: 80%
+
 
 
 Analysis of Speech Datasets
@@ -154,22 +161,25 @@ After that it is worth to check words with zero accuracy.
 
     .. image:: images/sde_mls_words.png
         :align: center
+        :width: 800px
         :alt: MLS Words
-        :scale: 50%
+
 
 And then look at high CER utterances.
 
     .. image:: images/sde_mls_cer.png
         :align: center
+        :width: 800px
         :alt: MLS CER
-        :scale: 50%
+
 
 Listening to the audio recording helps to validate the corresponding reference transcript.
 
     .. image:: images/sde_mls_player.png
         :align: center
+        :width: 800px
         :alt: MLS Player
-        :scale: 50%
+
 
 
 
diff --git a/docs/update_docs_docker.sh b/docs/update_docs_docker.sh
@@ -1,3 +1,5 @@
 cd ../
 docker run --rm -v $PWD:/workspace python:3.8 /bin/bash -c "cd /workspace && \
 pip install -r requirements/requirements_docs.txt && cd docs/ && rm -rf build && make clean && make html && make html"
+echo "To start web server just run in docs directory:"
+echo "python3 -m http.server 8000 --directory ./build/html/"